A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
PALO: a probabilistic hill-climbing algorithm
1996
Artificial Intelligence
Many learning systems search through a space of possible performance elements, seeking an element whose expected utility, over the distribution of problems, is high. As the task of finding the globally optimal element is often intractable, many practical learning systems instead hillclimb to a local optimum. Unfortunately, even this is problematic as the learner typically does not know the underlying distribution of problems, which it needs to determine an element's expected utility. This paper
doi:10.1016/0004-3702(95)00040-2
fatcat:gqjfb7nxibhslnlc4ib7jhjqjy